Bingxu Zhong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Bingxu Zhong has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Fuqaing Cai
South China University of Technology
1 shared publication - Hongli Du
School of Biology and Biological Engineering, South China University of Technology, Guangzhou, 510006, China.
1 shared publication - Hui Lu
State Key Laboratory of Microbial Metabolism, Joint International Research Laboratory of Metabolic and Developmental Sciences, School of Life Sciences and Biotechnology, Shanghai Jiao Tong University, Shanghai, China
1 shared publication - Jerome Rumdon Lon
School of Biology and Biological Engineering, South China University of Technology
1 shared publication - Kenta Nakai
Laboratory of functional analysis in silico, Human Genome Center, The University of Tokyo
1 shared publication - Mingqi Jiao
Key Laboratory of Systems Health Science of Zhejiang Province, School of Life Science, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, China
1 shared publication
Latest Publications
- Open Access
- 22 April 2026
- Published by Springer Nature in Nature Communications
- Vol. 17
CellNiche represents cellular microenvironments in atlas-scale spatial omics data with contrastive learning
Deciphering cellular microenvironments at atlas scale remains challenging because molecular identity, spatial context, and platform heterogeneity are tightly coupled. Here we present CellNiche, a scalable contrastive-learning framework that identifies and characterizes cellular microenvironments from spatial omics data using cell-centric spatial-proximity subgraphs. CellNiche combines spatial co-localization and molecular co-expression cues to learn microenvironment-aware embeddings. Across spatial omics datasets from multiple platforms (>10 million cells in total), scaling experiments show improved representations with more training data and competitive clustering and embedding-quality performance with efficient computation. In a multi-sample human non-small-cell lung cancer (NSCLC) cohort, CellNiche identifies conserved and sample-specific tumor and immune microenvironments and captures localized spatial transitions. In four independent mouse brain atlases, CellNiche integrates 293 slices into a unified virtual brain map for cross-atlas annotation transfer and spatial refinement.
- 22 April 2026
- Published by Springer Nature in Nature Communications
- Vol. 17
Open AccessCellNiche represents cellular microenvironments in atlas-scale spatial omics data with contrastive learning
Deciphering cellular microenvironments at atlas scale remains challenging because molecular identity, spatial context, and platform heterogeneity are tightly coupled. Here we present CellNiche, a scalable contrastive-learning framework that identifies and characterizes cellular microenvironments from spatial omics data using cell-centric spatial-proximity subgraphs. CellNiche combines spatial co-localization and molecular co-expression cues to learn microenvironment-aware embeddings. Across spatial omics datasets from multiple platforms (>10 million cells in total), scaling experiments show improved representations with more training data and competitive clustering and embedding-quality performance with efficient computation. In a multi-sample human non-small-cell lung cancer (NSCLC) cohort, CellNiche identifies conserved and sample-specific tumor and immune microenvironments and captures localized spatial transitions. In four independent mouse brain atlases, CellNiche integrates 293 slices into a unified virtual brain map for cross-atlas annotation transfer and spatial refinement.
- Open Access
- 12 December 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (24) , 3169
Toward Graph-Based Decoding of Tumor Evolution: Spatial Inference of Copy Number Variations
Background/Objectives: Constructing a comprehensive spatiotemporal map of tumor heterogeneity is essential for understanding tumor evolution, with copy number variation (CNV) being a significant feature. Existing studies often rely on tools originally developed for single-cell data, which fail to utilize spatial information, often leading to an incomplete map of clonal architecture. Our study aims to develop a model that fully leverages spatial omics data to elucidate spatio-temporal changes in tumor evolution. Methods: Here, we introduce SCOIGET (Spatial COpy number Inference by Graph on Evolution of Tumor), a novel framework using graph neural networks with graph attention layers to learn spatial neighborhood features of gene expression and infer copy number variations. This approach integrates spatial multi-omics features to create a comprehensive spatial map of tumor heterogeneity. Results: Notably, SCOIGET achieves a substantial reduction in error metrics (e.g., mean squared error, cosine similarity, and distance measures) and produces superior clustering performance, as indicated by higher Silhouette Scores compared to existing methods, validated by both simulated data with spot-level ground truth and patient cohorts. Our model significantly enhances the accuracy of tumor evolution depiction, capturing detailed spatial and temporal changes within the tumor microenvironment. It is versatile and applicable to various downstream tasks, demonstrating strong generalizability across different spatial omics platforms, including 10× Visium and Visium HD and various cancer types, including colorectal cancer and prostate cancer. This robust performance improves research efficiency and provides valuable insights into tumor progression. Conclusions: SCOIGET offers an innovative solution by integrating multiple features and advanced algorithms, providing a detailed and accurate representation of tumor heterogeneity and evolution, aiding in the development of personalized cancer treatment strategies.
- 12 December 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (24) , 3169
Open AccessToward Graph-Based Decoding of Tumor Evolution: Spatial Inference of Copy Number Variations
Background/Objectives: Constructing a comprehensive spatiotemporal map of tumor heterogeneity is essential for understanding tumor evolution, with copy number variation (CNV) being a significant feature. Existing studies often rely on tools originally developed for single-cell data, which fail to utilize spatial information, often leading to an incomplete map of clonal architecture. Our study aims to develop a model that fully leverages spatial omics data to elucidate spatio-temporal changes in tumor evolution. Methods: Here, we introduce SCOIGET (Spatial COpy number Inference by Graph on Evolution of Tumor), a novel framework using graph neural networks with graph attention layers to learn spatial neighborhood features of gene expression and infer copy number variations. This approach integrates spatial multi-omics features to create a comprehensive spatial map of tumor heterogeneity. Results: Notably, SCOIGET achieves a substantial reduction in error metrics (e.g., mean squared error, cosine similarity, and distance measures) and produces superior clustering performance, as indicated by higher Silhouette Scores compared to existing methods, validated by both simulated data with spot-level ground truth and patient cohorts. Our model significantly enhances the accuracy of tumor evolution depiction, capturing detailed spatial and temporal changes within the tumor microenvironment. It is versatile and applicable to various downstream tasks, demonstrating strong generalizability across different spatial omics platforms, including 10× Visium and Visium HD and various cancer types, including colorectal cancer and prostate cancer. This robust performance improves research efficiency and provides valuable insights into tumor progression. Conclusions: SCOIGET offers an innovative solution by integrating multiple features and advanced algorithms, providing a detailed and accurate representation of tumor heterogeneity and evolution, aiding in the development of personalized cancer treatment strategies.
- Open Access
Prediction and Evolution of B Cell Epitopes of Surface Protein in SARS-CoV-2
The discovery of epitopes is helpful to the development of SARS-CoV-2 vaccine. The sequences of the surface protein of SARS-CoV-2 and its proximal sequences were obtained by BLAST, the sequences of the whole genome of SARS-CoV-2 were obtained from the GenBank. Based on the NCBI Reference Sequence: NC_045512.2, the conformational and linear B cell epitopes of the surface protein were predicted separately by various prediction methods. Furthermore, the conservation of the epitopes, the adaptability and other evolutionary characteristics were also analyzed. 7 epitopes were predicted, including 5 linear epitopes and 2 conformational epitopes, one of the linear and one of the conformational were coincide. The epitope D mutated easily, but the other epitopes were very conservative and the epitope C was the most conservative. It is worth mentioning that all of the 6 dominated epitopes were absolutely conservative in nearly 1000 SARS-CoV-2 genomes, and they deserved further study. The findings would facilitate the vaccine development, had the potential to be directly applied on the treatment in this disease, but also have the potential to prevent the possible threats caused by other types of coronavirus.
Open AccessPrediction and Evolution of B Cell Epitopes of Surface Protein in SARS-CoV-2
The discovery of epitopes is helpful to the development of SARS-CoV-2 vaccine. The sequences of the surface protein of SARS-CoV-2 and its proximal sequences were obtained by BLAST, the sequences of the whole genome of SARS-CoV-2 were obtained from the GenBank. Based on the NCBI Reference Sequence: NC_045512.2, the conformational and linear B cell epitopes of the surface protein were predicted separately by various prediction methods. Furthermore, the conservation of the epitopes, the adaptability and other evolutionary characteristics were also analyzed. 7 epitopes were predicted, including 5 linear epitopes and 2 conformational epitopes, one of the linear and one of the conformational were coincide. The epitope D mutated easily, but the other epitopes were very conservative and the epitope C was the most conservative. It is worth mentioning that all of the 6 dominated epitopes were absolutely conservative in nearly 1000 SARS-CoV-2 genomes, and they deserved further study. The findings would facilitate the vaccine development, had the potential to be directly applied on the treatment in this disease, but also have the potential to prevent the possible threats caused by other types of coronavirus.